检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Pan, Mei-Hong Xin, Hong-Yi Xia, Chun-Qiu Shen, Hong-Bin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiaotong University Shanghai200240 China

Few-shot classification aims to learn a classifier that categorizes objects of unseen classes with limited samples. One general approach is to mine as much information as possible from limited samples. This can be achieved by incorporating data from multiple modals. However, existing multi-modality methods only use additional modality in support samples while adhering to a single modal in query samples. Such approach could lead to information imbalance between support and query samples, which confounds model generalization from support to query samples. Towards this problem, we propose a task-adaptive semantic feature learning mechanism to incorporate semantic features for both support and query samples. The semantic feature learner is trained episodic-wisely by regressing from the feature vectors of the support samples. It is utilized to predict semantic features for the query samples. Such method maintains a consistent training scheme between support and query samples and enables direct model transfer from support to query data, which significantly improves model generalization. We conduct extensive experiments on four benchmarks in both inductive and tranductive settings. Results show that the proposed TasNet outperforms state-of-the-art methods with an improvement of 1% to 5% in classification accuracy, demonstrating the superiority of our method. The exhaustive ablation studies further validate the effectiveness of our framework. © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Venous Thromboembolism Using Recurrent Neural Networks with Time-Series Data 24

Detection of Venous Thromboembolism Using Recurrent Neural N...

引用

3rd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2024

作者： Xu, Can Huang, Yaqin Xiang, Xinni Lei, Haike Yang, Jie Shanghai Jiao Tong University Shanghai China Chongqing University Cancer Hospital Chongqing China West China Hospital Sichuan University Chengdu China Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition China Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment China West China School of Medicine China Chongqing Cancer Multi-omics Big Data Application Engineering Research Center China

ISBN: (纸本)9798400716416

Machine Learning (ML) has been widely applied to medical science for decades. As common knowledge, the progress of many diseases is often chronic and dynamic. Longitudinal data, or time-series data, has better descriptions of certain diseases, as it naturally captures the dynamic over time. Venous thromboembolism (VTE), as a regular complication of cancer tumour treatments, has been emphasized in many studies. Recent research has shown that ML algorithms incredibly contribute to VTE risk estimation and prediction. However, existing methods rarely consider the dynamic changes during the development of VTE, and often make decisions based on time-point data, such as the latest blood test results of patients. In this paper, we propose a VTE detection model that takes advantage of capturing dynamic information using time-series data. The model consists of a Recurrent Neural Network (RNN) based framework with time embedding and Attention mechanism to encode longitudinal features of patients. We test our proposed model on a real-world dataset that contains multiple times of blood test results of patients together with other clinical features. The network is compared with several commonly used ML models in previous VTE studies. The results show that our model outperforms all baseline models, and achieved a state-of-art performance with 80.0% accuracy and 0.881 AUC. © 2024 ACM.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Dim small targets fusion detection in infrared image

Dim small targets fusion detection in infrared image

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Yu-Qiu Sun Yu Zheng Jin-Wen Tian Jian Liu School of Information and Mathematics Yangtze University Jingzhou China State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China State Education Commission Key Laboratory for Image Processing and Intelligent Control Department of Electronic Information and Enginery of Huazhong University of Science and Technology Wuhan China

To infrared images, the contrast of target and background is low, dim small targets have no concrete shapes and their textures cannot be reliable predicted. The paper puts forward a novel algorithm to fuse mid-wave and long-wave infrared images and detect targets. Firstly, the source images are decomposed by wavelet transformation. In usual, targets in infrared images are man-made, and their fractal dimension is different comparing with natural background. In wavelet transformation domain high-frequency part, we calculate local fractal dimension and set up fusion rule to merge corresponding sub-images of two matching source images. In low-frequency, we extract local maximum gray level to fuse them. Then reconstruct image by wavelet inverse transformation and obtain fused result image. In fusion results, the contrast between targets and background has obvious changes. And targets can be detected using contrast threshold. The experimental results show that the method proposed in this paper using wavelet transformation fractal dimension to fuse dual band infrared images, and then detect targets is better than using mid-wave or long -wave infrared images detect targets alone.

关键词： Fractals Wavelet transforms Pixel Object detection Fuses Approximation methods Manganese

来源：评论

学校读者我要写书评

暂无评论

Interactive object segmentation using iterative adjustable graph cut

Interactive object segmentation using iterative adjustable g...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Ran Shi Zhi Liu Yinzhu Xue Xiang Zhang School of Communication and Information Engineering Shanghai University Shanghai China Key Laboratory of Advanced Display and System Application Ministry of Education Shanghai University Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China

Interactive object segmentation is widely used for extracting any user-interested objects from natural images. A common problem with many interactive segmentation approaches is that the object segmentation quality is degraded due to inaccurate object/background seeds provided by the user. This paper proposes an iterative adjustable graph cut to efficiently solve this problem. First, object/background seeds are initialized based on the object segmentation result obtained with the user-specified scribbles as the interactive input. Then, an iterative seed adjustment scheme is exploited to correct inaccurate seeds and extract new suitable seeds via graph cut, in which the balancing weight between energy terms are adaptively updated to protect stable seeds and speedup the iteration process. Finally, suitable seeds are obtained and graph cut is used to segment the objects. Experimental results demonstrate the better segmentation performance of our approach even if user provides rather rough seeds.

关键词： Object segmentation Image segmentation Reliability Iterative methods Educational institutions Image color analysis Error analysis

来源：评论

学校读者我要写书评

暂无评论

Target recognition method based on template matching in downward-looking infrared image

Target recognition method based on template matching in down...

引用

International Conference on Audio, Language and Image processing, ICALIP

作者： Hu Zhu Lizhen Deng Gang Zhou Xiaodong Bai Gaihua Wang National Key Laboratory of Science and Technology on Multi-spectral Information Processing Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China College of Electrical & Electronic Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781467301732

Automatic ground target recognition technology in downward-looking infrared imagery is challenging problems due to the complexity of real-world. A robust ground target recognition method is proposed for downward-looking infrared (DLIR) image sequences in this paper. A complete model of the proposed method is designed firstly and the principles of some key technologies are introduced as following. Perspective transformation is used to solve the projective problems of landmark translation, rotation and scale variance in real-time image sequence. The size of landmark is estimated real-timely by using flight parameters and imaging parameters for getting the model with an appropriate scale. Based on the matching results of landmark and flight parameters, target position technology is proposed to identify the position of target by using the position relation between landmark and target. Experimental results using real-world image data with complicated background showed that the proposed method not only causes high precisely locating results, but also has good robustness for target occlusion.

关键词： Target recognition Satellites Image sequences Real-time systems Robustness Imaging Aircraft

来源：评论

学校读者我要写书评

暂无评论

Abundant Semantic Information Module for Object Detection

Abundant Semantic Information Module for Object Detection

引用

Algorithms, High Performance Computing and Artificial Intelligence (AHPCAI), International Conference on

作者： Taida Wu Qishen Li Qiufeng Li Jun Gao School of Information Engineering Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Jiangxi China School of Software Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Nondestructive Testing (Ministry of Education) Nanchang Hangkong University Nanchang Jiangxi China

Nowadays, with the high-speed iteration of convolution neural network, the efficient object detector emerges one after another. As an important branch of computer vision, object detection aims to detect where and what the object is. However, nowadays, many detector cannot extract abundant semantic information to discriminate the location and size of the objects, resulting in poor performance of the network. In this paper, a new module is proposed, named Abundant Semantic Information Module (ASIM), to enrich and expand the semantic information of the object with more and larger receptive fields. In ASIM, we blend the extracted feature maps to different degrees with different blending factors and fuse them so that all object information is given full attention. Compared to the baseline method, a wealth of experiments show that our module has achieved a significant performance improvement.

关键词： Location awareness Fuses High performance computing Semantics Neural networks Object detection Detectors

来源：评论

学校读者我要写书评

暂无评论

A fast VLSI architecture for two-dimensional discrete wavelet transform based on lifting scheme [image compression applications]

A fast VLSI architecture for two-dimensional discrete wavele...

引用

International Conference on Solid-State and Integrated Circuit Technology

作者： Chengyi Xiong Jinwen Tian Jian Liu College of Electronic Information Engineering South-Center University of Science and Technology Wuhan China Institute of Pattern Recognition & Artification Intelligence Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)078038511X

This paper proposes a novel fast architecture for a 2D discrete wavelet transform by using a lifting scheme, Parallel and embedded decimation techniques are employed to optimize the architecture, which is mainly composed of two horizontal filter modules and one vertical filter module, working in parallel and pipeline fashion with 100% hardware utilization. The architecture is designed to generate two outputs in one working clock cycle, with every two subbands coefficients alternately. The total time for computing J levels of decomposition for an N/spl times/N image is approximately 2N/sup 2/(1-4/sup -J/)/3 clock cycles. In comparison with the other devices reported in previous literature, the design has many advantages including lower hardware complexity and area and power efficiency. The design is also fast, regular and simple, as well as well suited for VLSI implementation.

关键词： Discrete wavelet transforms Very large scale integration Filters Computer architecture Wavelet transforms Hardware Clocks Image coding Matrix converters Pipelines

来源：评论

学校读者我要写书评

暂无评论

Low-light image enhancement model based on self-calibration illumination and color adjustment

Low-light image enhancement model based on self-calibration ...

引用

Algorithms, High Performance Computing and Artificial Intelligence (AHPCAI), International Conference on

作者： Guiwen Zhang Qishen Li Qiufeng Li Taida Wu School of Information Engineering Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Jiangxi China School of Software Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Nondestructive Testing (Ministry of Education) Nanchang Hangkong University Nanchang Jiangxi China

to improve the clarity of objects in a dark-light environment, and to facilitate the identification and detection of targets behind. People perceive the color and brightness of a point not only depending on the pixel value of the point but also the absolute light entering the human eye is related to the color and brightness around the point. The self-calibration model we used considers the surrounding information, which avoids the information pollution, such as large regions of dark background information. In this model, we introduce a heterogeneous convolution filter, which makes reasonable use of different parts of the filter. Through this operation, information from multiple different scale spaces can be fused, and the field of view when applying the convolution layer is greatly increased without increasing the hyper-parameters, thus producing a more distinctive feature representation. Then the self-calibration model is combined with the backbone reinforcement network, which can not only retain the information of the original scale space but also efficiently collect the latent space information to guide the feature transformation in the original space. After the different channels of the image are processed separately, the dependency between the channels can be established by using the heterogeneous convolution filter. Finally, the test on the ExDark data set proves that our dark target enhancement effect has been significantly improved.

关键词： Training Pollution Image color analysis Convolution Brightness Lighting Information filters

来源：评论

学校读者我要写书评

暂无评论

A novel line based connected component labeling algorithm

A novel line based connected component labeling algorithm

引用

International Conference on Computer Science and Information Technology (CSIT)

作者： Yebin Fan Shengsheng Yu Hualong Zhao Department of Computer Science Huazhong University of Science and Technology Wuhan China National Key Laboratory of Science and Technology on Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

This paper presents a fast connected component labeling algorithm based on line description method and optimized tree Union-Find strategy. The algorithm transforms the pixel-connected issue, which most of proposed algorithms focus on, into line-connected issue. This algorithm is comprised of three phrases, line extraction, connected component identification and label assignment. The line description method transforms the connected pixels into line form for reducing the scan time. While the new tree Union-Find strategy diminishes the redundant root compare operations. A comparison analysis is performed with other optimized famous component labeling algorithms. Our algorithm has shown an outstanding performance with respect to the processing time, which achieves 1.1~8 times as fast as the other algorithms in various test cases.

关键词： Noise

来源：评论

学校读者我要写书评

暂无评论

Gait recognition Algorithm GCGait based on Skeleton

Gait Recognition Algorithm GCGait based on Skeleton

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Ru Ma Jikai Zhang Mengyu Jia Xiaoqi Lv School of Information Engineering Inner Mongolia University of Science and Technology Baotou China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Baotou China School of Information Engineering Inner Mongolia University of Technology Hohhot China

To solve the problem of low accuracy of gait recognition in complex scenes, a novel skeleton-based gait recognition algorithm, GCGait, is proposed. Taking human posture as the input of gait feature, the interference caused by wearing changes and other factors is reduced. To extract sufficient input features, multi-branch input is used in the early stage of the model. By introducing the multi-attention mechanism, the network can learn the semantic information of the non-directly connected joints, excavate the most discriminative features from complex videos, and further improve the recognition performance. In order to reduce the influence of cross view, the fusion loss function is used in the experiment. Experimental results show that the average recognition rate of the proposed algorithm on the CASIA-B dataset is improved by 5.2%, and the average recognition accuracy on the OU-MVLP dataset is increased by 66.3%, which proves the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：